Abstract. Games are considered important benchmark tasks of artificial intelligence research. Modern strategic board games can typically be played by three or more people, which m...
Abstract— This paper describes experiments using reinforcement learning techniques to compute pattern urgencies used during simulations performed in a Monte-Carlo Go architecture...
In the last decade, proof-number search and Monte-Carlo methods have successfully been applied to the combinatorial-games domain. Proof-number search is a reliable algorithm. It re...
Jahn-Takeshi Saito, Guillaume Chaslot, Jos W. H. M...
We present a way to integrate search and Monte-Carlo methods in the game of Go. Our program uses search to find the status of tactical goals, builds groups, selects interesting go...